AGENT SKILLS

Skills over MCP: an MCP server whose tools are a skill directory, so agents pay context only for what a task needs. The argument and a working implementation.

Agent config files like Claude Code hooks, Cursor rules and VS Code tasks can trigger code. Why they need review like dependencies, and what to check first.

Taste skills for AI agents turn subjective review criteria into executable infrastructure. What trending anti-slop and compound-engineering skills signal.

Agent skills are becoming package managers. Why coding teams need dependency governance for the instructions their agents inherit, not more prompts.

Claude Code's newer plugin URL and hard-deny controls are small release-note items with a big implication: agent extensions now need supply-chain discipline.

Matt Pocock's skills repo is a signal for AI coding teams: treat skills as governed production controls, not a folder of viral prompts.

Matt Pocock's Claude Code skills repo shows the useful direction for agent workflows: small, composable skills that encode engineering discipline instead of hiding it.

Agent skills work when they carry exit criteria. What Addy Osmani's agent-skills repo gets right about turning AI coding advice into engineering checklists.

Google's skills repo shows the next agent playbook: product-specific operating instructions that turn docs into executable procedures for coding agents.

The viral andrej-karpathy-skills CLAUDE.md shows agent rules are product surface: what the file teaches, what to keep, and what to change before copying.